arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

AAAI Conference on Artificial Intelligence · 会议 · Artificial Intelligence

共收录 9567
2603.28772 2026-04-01 cs.DC

Federated Inference for Heterogeneous LLM Communication and Collaboration

联邦推断用于异构大语言模型通信与协作

Zihan Chen, Zeshen Li, Howard H. Yang, Tony Q. S. Quek, Jihong Park

AI总结 本文提出FedRefine框架,解决多LLM协作中的性能、隐私和异构性问题,通过隐私保护的KV缓存通信提升设备端推断能力。

Comments 6 pages. Accepted by AAAI 2026 Workshop on ML4Wireless

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.09176 2026-04-01 cs.LG

$D^2Prune$: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness

$D^2Prune$:通过双重泰勒展开和注意力分布意识对大型语言模型进行稀疏化

Lang Xiong, Ning Liu, Ao Ren, Yuheng Bai, Haining Fang, BinYan Zhang, Zhe Jiang, Yujuan Tan, Duo Liu

AI总结 本文提出$D^2Prune$方法,通过双重泰勒展开和注意力分布意识,解决现有剪枝方法在激活分布偏移和注意力模块长尾分布方面的不足,提升模型压缩效果。

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(32), 27171-27179, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07204 2026-04-01 cs.AI cs.CY cs.MA

Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations

通过LLM赋能的反事实模拟评估在线 moderation

Giacomo Fidone, Lucia Passaro, Riccardo Guidotti

AI总结 本文提出一种基于LLM的反事实模拟方法,用于评估在线社交网络的 moderation 策略,揭示了社交传染现象及个性化策略的有效性。

Comments Accepted for publication at AAAI Conference on Artificial Intelligence 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.13242 2026-03-31 cs.CY

AI Unplugged: Embodied Interactions for AI Literacy in Higher Education

AI 无插件:面向高等教育的具身互动以促进AI素养

Jennifer M. Reddig, Scott Moon, Kaitlyn Crutcher, Christopher J. MacLellan

AI总结 本文提出一种将具身无插件活动融入大学AI入门课程的新教学方法,通过互动游戏帮助学生理解AI概念,促进概念与技术技能的结合。

Journal ref In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 47, pp. 40679-40687). 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
1906.05284 2026-03-31 eess.IV cs.CV cs.LG

Image-Adaptive GAN based Reconstruction

基于图像自适应的GAN重建

Shady Abu Hussein, Tom Tirer, Raja Giryes

机构 * School of Electrical Engineering Tel Aviv University(特拉维夫大学电气工程学院)

AI总结 本文提出图像自适应GAN方法,通过改进生成器的表示能力并利用反投影确保恢复与观测一致,提升图像超分辨率和压缩感知的性能。

Comments Published to AAAI 2020. Code available at https://github.com/shadyabh/IAGAN

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.28003 2026-03-31 cs.CV

DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video

DipGuava:解耦个性化高斯特征以从单目视频生成3D头部虚拟人物

Jeonghaeng Lee, Seok Keun Choi, Zhixuan Li, Weisi Lin, Sanghoon Lee

AI总结 本文提出DipGuava方法,通过解耦面部外观为两个互补组件,从单目视频生成具有个性化特征的3D头部虚拟人物,提升真实感和表现力。

Comments AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14262 2026-03-31 cs.LG cs.AI

Object-Centric World Models for Causality-Aware Reinforcement Learning

基于因果意识的强化学习对象中心世界模型

Yosuke Nishimoto, Takashi Matsubara

AI总结 本文提出STICA框架,通过对象中心Transformer构建世界模型,并结合因果意识策略和价值网络,提升样本效率和最终性能。

Comments Accepted by AAAI-26. Codes are available at https://github.com/nishimoto0430/STICA

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27321 2026-03-31 cs.LG cs.AI

Multimodal Forecasting for Commodity Prices Using Spectrogram-Based and Time Series Representations

基于频谱和时间序列表示的商品价格多模态预测

Soyeon Park, Doohee Chung, Charmgil Hong

机构 * Impactive AI

AI总结 本文提出SEMF方法,结合频谱和时间序列表示,提升多变量时间序列预测的准确性与鲁棒性,通过多模态融合和频谱编码在多个商品价格预测任务中优于七种基线模型。

Comments AAAI 2026 Summer Symposium Series; 9 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27011 2026-03-31 cs.SI

ParsCN: A Persian Dataset for Counter-Narrative Generation to Combat Online Hate Speech

ParsCN:一种针对网络仇恨言论的Persian数据集用于生成反叙事以对抗在线仇恨言论

Zahra Safdari Fesaghandis, Suman Kalyan Maity

AI总结 本文提出ParsCN数据集,用于生成对抗网络仇恨言论的反叙事,通过结合文化导向的人工标注与少样本LLM增强生成,提升低资源语言的反叙事质量。

Comments Accepted at the International AAAI Conference on Web and Social Media (ICWSM 2026); Paper Information: 16 pages, 3 Figures, 10 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.08120 2026-03-31 cs.LG

Structure Detection for Contextual Reinforcement Learning

上下文强化学习中的结构检测

Tianyue Zhou, Jung-Hoon Cho, Cathy Wu

AI总结 本文提出SD-MBTL框架,通过动态识别CMDP的通用化结构,选择合适的MBTL算法,提升多任务学习性能,实验显示其在连续控制、交通控制和农业管理等任务中表现优于现有方法。

Journal ref AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12727 2026-03-31 math.LO cs.LO

A Topological Rewriting of Tarski's Mereogeometry

塔尔斯基 mereogeometry 的拓扑重写

Patrick Barlatier, Richard Dapoigny

AI总结 本文通过扩展基于依赖类型理论的 lambda-MM 库,结合白头点自由解释,将塔尔斯基几何学与拓扑关系结合,构建出新的拓扑结构,并证明了 mereological 类别与正则开集的对应关系,扩展了理论的表达能力。

Comments This is the full version of the paper accepted at AAAI-26. The arXiv version includes the complete list of authors

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14376 2026-03-31 cs.CV

DOS: Directional Object Separation in Text Embeddings for Multi-Object Image Generation

DOS:文本嵌入中多对象图像生成的定向对象分离

Dongnam Byun, Jungwon Park, Jungmin Ko, Changin Choi, Wonjong Rhee

AI总结 本文提出DOS方法,通过修改CLIP文本嵌入提升多对象图像生成效果,减少对象混合,实验表明其在多对象生成中表现更优。

Comments Accepted to AAAI 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 37235. (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09428 2026-03-31 cs.CV cs.AI

What-Meets-Where: Unified Learning of Action and Contact Localization in Images

何与何:统一图像中动作与接触定位的学习

Yuxiao Wang, Yu Lei, Wolin Liang, Weiying Xue, Zhenao Wei, Nan Zhuang, Qi Liu

AI总结 本文提出PaIR-Net框架,通过同时预测高阶动作语义和细粒度身体接触区域,解决动作与接触定位的联合建模问题,实验表明其优于基线方法。

Comments Accepted by AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.16906 2026-03-31 cs.CV

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation

自修正流蒸馏用于一致的一步和少步文本到图像生成

Quan Dao, Hao Phung, Trung Dao, Dimitris Metaxas, Anh Tran

AI总结 本文提出自修正流蒸馏方法,结合一致性模型和对抗训练,提升文本到图像生成的一致性与效率,实验验证其在CelebA-HQ和COCO数据集上的优越性能。

Comments Accepted to AAAI 2025. Code: https://github.com/hao-pt/SCFlow.git

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.26743 2026-03-31 cs.CV cs.AI cs.LG

Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)

引导稀疏解码器潜在特征以控制动态头部剪枝在视觉变换器中(学生摘要)

Yousung Lee, Dongsoo Har

AI总结 本文提出结合稀疏解码器与动态剪枝的新框架,通过稀疏潜在特征实现头部剪枝的可解释和可控,提升ViTs的效率和可解释性。

Comments 3 pages, 5 figures. Accepted as AAAI 2026 Student Abstract. Includes additional appendix with extended analysis

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2026), Vol. 40, No. 48, pp. 41263-41265

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.11601 2026-03-30 cs.AI

See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay

看见、符号化、行动:通过空间表示接地VLMs以实现更好的游戏表现

Ashish Baghel, Paras Chopra

AI总结 本文研究了通过提供视觉帧和场景符号表示来提升VLMs在交互环境中的表现,发现准确的符号信息能提升性能,但自身提取符号的模型性能受模型能力和场景复杂度影响。

Comments 11 pages, 13 figures. Accepted to LMReasoning Workshop at AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.20931 2026-03-30 cs.DS cs.DM

Finding Diverse Solutions Parameterized by Cliquewidth

基于团宽的多样化解寻找

Karolina Drabik, Tomáš Masařík

AI总结 本文基于团宽参数,研究如何以较低开销生成多样化解,证明MSO_1可表问题在团宽参数下可线性FPT时间内求解,扩展了结构图参数和逻辑在多样化问题中的复杂性景观。

Comments Accepted at AAAI 2026: the 40th Annual AAAI Conference on Artificial Intelligence, 30 pages, 3 figure

Journal ref Proceedings: (AAAI 2026) AAAI Conference on Artificial Intelligence, 40(43), 36864-36872

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.18248 2026-03-30 cs.AI

Extreme Value Monte Carlo Tree Search for Classical Planning

极值理论在经典规划中的蒙特卡洛树搜索

Masataro Asai, Stephen Wissow

AI总结 本文提出UCB1-Uniform算法,利用极值理论解决经典规划中带宽不足和全贝尔曼备份缺乏理论依据的问题,证明了算法的 regret 绑定并验证了其在经典规划中的性能。

Comments Accepted in AAAI-26. arXiv admin note: substantial text overlap with arXiv:2305.09840 (background section)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06663 2026-03-27 cs.CV cs.AI

Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting

图标记:通过基于图的视觉提示提升多模态语言模型的空间推理能力

Giacomo Frisoni, Lorenzo Molfetta, Mattia Buzzoni, Gianluca Moro

机构 * University of Bologna(博洛尼亚大学)

AI总结 本文提出Graph-of-Mark,一种基于图的视觉提示方法,通过在输入图像上叠加场景图来增强多模态语言模型的空间推理能力,实验表明其在视觉问答和定位任务中提升了11个百分点的准确率。

Comments Please cite the definitive, copyrighted, and peer-reviewed version of this article published in AAAI 2026, edited by Sven Koenig et al., AAAI Press, Vol. 40, No. 36, Technical Track, pp. 30726-30734, 2026. DOI: https://doi.org/10.1609/aaai.v40i36.40329

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.12760 2026-03-27 cs.MM cs.AI cs.CV

A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis

一种用户友好的生成模型偏好提示框架

Nailei Hei, Qianyu Guo, Zihao Wang, Yan Wang, Haofen Wang, Wenqiang Zhang

AI总结 本文提出UF-FGTG框架,通过粗细粒度提示数据集和自适应特征提取模块,自动优化用户输入提示以生成更高质量的图像。

Comments Accepted by The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.07047 2026-03-26 cs.CV cs.LG

ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees

ShapBPT:基于数据感知二进制划分树的图像特征归因

Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda

AI总结 本文提出ShapBPT,一种基于层次Shapley公式的数据感知图像可视化方法,通过多尺度二进制划分树结构提升图像特征归因的效率与语义意义。

Comments Presented at AAAI-26 conference and published in Proceedings of the The Fortieth AAAI Conference on Artificial Intelligence (AAAI-26)

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20001 2026-03-26 cs.CL cs.SI

A Machine Learning Approach for Detection of Mental Health Conditions and Cyberbullying from Social Media

从社交媒体检测心理健康状况和网络欺凌的一种机器学习方法

Edward Ajayi, Martha Kachweka, Mawuli Deku, Emily Aiken

机构 * Carnegie Mellon University Africa Kigali, Rwanda(卡内基梅隆大学非洲分校基加利分校,刚果(金))

AI总结 本文提出统一的多类分类框架,用于从社交媒体数据中检测十种不同的心理健康和网络欺凌类别,通过实验表明端到端微调对性能至关重要,MentalBERT模型在准确率和宏F1分数上表现优异。

Comments Best Paper Award at the AAAI-26 Bridge Program on AI for Medicine and Healthcare. Published in Proceedings of the Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 317:15-26, 2026. Paper URL: https://proceedings.mlr.press/v317/ajayi26a.html

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10051 2026-03-26 cs.CL

GraphIF: Enhancing Multi-Turn Instruction Following for Large Language Models with Relation Graph Prompt

GraphIF: 通过关系图提示增强大语言模型的多轮指令遵循

Zhenhe Li, Can Lin, Ling Zheng, Wen-Da Wei, Junli Liang, Qi Song

机构 * Zhenhe Li 1(李振和1) Can Lin 1(林灿1) Ling Zheng 1(郑凌1) Wen-Da Wei 2(韦文达2) Junli Liang 1(梁俊利1) Qi Song 1(宋琪1)

AI总结 GraphIF通过构建关系图结构,利用图提示提升大语言模型的多轮指令遵循能力,实验表明其在多轮对话评估指标上表现优异。

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.24023 2026-03-26 cs.CL cs.AI

Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale

内部架构:一种两阶段微调方法,用于大规模高效文本到SQL

Chinmay Soni, Shivam Chourasia, Gaurav Kumar, Hitesh Kapoor

AI总结 本文提出一种两阶段监督微调方法,使模型能内部化整个数据库架构,减少输入token至100以下,提升文本到SQL的精度和效率。

Comments 8 pages, 6 figures. Published in the Proceedings of the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 40(47) (2026) 40110-40117

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21910 2026-03-26 cs.CL cs.AI

AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition

AutoSCORE: 通过结构化组件识别提升多智能体大语言模型的自动评分

Yun Wang, Zhaojun Ding, Xuansheng Wu, Siyue Sun, Ninghao Liu, Xiaoming Zhai

AI总结 AutoSCORE通过多智能体大语言模型和结构化组件识别提升自动评分的准确性与可解释性,在多个基准数据集上表现出色,尤其在复杂评分标准下效果显著。

Comments 9 pages, 2 figures

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 40898-40906, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11733 2026-03-26 cs.MA cs.AI

SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication

SafeSieve: 从启发式到经验在基于大语言模型的多智能体通信中的渐进剪枝

Ruijia Zhang, Xinyan Zhao, Ruixiang Wang, Sigen Chen, Guibin Zhang, An Zhang, Kun Wang, Qingsong Wen

AI总结 本文提出SafeSieve,一种渐进适应的多智能体剪枝算法,通过双重机制动态优化智能体间通信。实验显示其在多个基准上实现了高准确率并显著降低token使用量,同时在异构环境下保持性能。

Comments AAAI-2026 poster; 7 pages for main content, 5 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08379 2026-03-25 cs.AI cs.LG

SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models

SOM方向优于单一方向:语言模型中的多方向拒绝抑制

Giorgio Piras, Raffaele Mura, Fabio Brau, Luca Oneto, Fabio Roli, Battista Biggio

AI总结 本文提出利用自组织映射(SOM)提取多方向拒绝特征,通过分析有害提示表示与无害提示表示的差异,验证了多方向抑制方法在提升模型安全性和拒绝能力上的有效性。

Comments Accepted at AAAI 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22812 2026-03-25 cs.CL

Efficient Hallucination Detection: Adaptive Bayesian Estimation of Semantic Entropy with Guided Semantic Exploration

高效幻觉检测:基于适应性贝叶斯估计的语义熵与引导语义探索

Qiyao Sun, Xingming Li, Xixiang He, Ao Cheng, Xuanyu Ji, Hailun Lu, Runke Huang, Qingyong Hu

AI总结 本文提出一种适应性贝叶斯估计框架,通过动态调整采样预算提升幻觉检测效率,在低预算场景下减少50%样本使用并提升AUROC 12.6%。

Comments Accepted to a AAAI 2026 (Oral Presentation, <5% acceptance rate), Project page: https://qingyonghu.github.io/Efficient-Hallucination-Detection/

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22721 2026-03-25 cs.AI

HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment

HyFI:超几何特征插值用于脑-视觉对齐

Sangmin Jo, Wootaek Jeong, Da-Woon Heo, Yoohwan Hwang, Heung-Il Suk

AI总结 本文提出HyFI框架,通过超几何空间插值融合和压缩视觉特征,解决脑信号与图像信息层级差异及语义特征纠缠问题,提升脑-视觉对齐效果。

Comments 17 pages, 13 figures. Published in AAAI 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 40, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17075 2026-03-25 cs.CL cs.LG

Perturb Your Data: Paraphrase-Guided Training Data Watermarking

扰动你的数据:基于改写引导的训练数据水印

Pranav Shetty, Mirazul Haque, Petr Babkin, Zhiqiang Ma, Xiaomo Liu, Manuela Veloso

AI总结 本文提出SPECTRA方法,通过LLM改写文本并结合评分模型,实现训练数据可靠检测,即使数据占比低于0.001%。该方法能有效区分训练数据与非训练数据,具有高鲁棒性和可扩展性。

Comments Accepted to AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏